Cesar Diaz | Universidad de los Andes (Colombia) (original) (raw)

Papers by Cesar Diaz

This article presents the results of four research projects carried out by the group Smart Cities... more This article presents the results of four research projects carried out by the group Smart Cities of the RUMBO Network. The research was developed in response to the integration of technologies with the well-being of citizens, focusing on the city of Bogota. The systematization of shopkeepers allowed to identify in this first phase the main needs of shopkeepers and establish the way they control inventories, relationships with customers and the environment, through software that they access from their smartphones. Industrial Safety Training System Based on Virtual and Augmented Reality advanced in the design of a prototype made in 3D to train operators on industrial safety and machinery handling, through activities focused on the use of PPE for operators. The digital training proposal that strengthens the teaching and learning exercise in teachers and impacts the Impacts the Students’ Skills Development analyzed the needs of teachers in digital skills, based on national standards an...

2013 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, 2013

Communications in Computer and Information Science, 2012

2011 International Conference on High Performance Computing & Simulation, 2011

2011 IEEE 11th International Conference on Computer and Information Technology, 2011

2014 14th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, 2014

ABSTRACT This poster shows the performance evaluation of UnaCloud Opportunistic Computing IaaS. W... more ABSTRACT This poster shows the performance evaluation of UnaCloud Opportunistic Computing IaaS. We analyze from an HPC perspective, two virtualization frameworks Virtual Box and VMware ESXi and compare them over this particular opportunistic cloud environment. The benchmarks consist of two set of tests, High Performance Linpack and IOzone, that examine the performance and the Input/Output response. The purpose of the experiments is to evaluate the behavior of the different virtual environments over an opportunistic cloud environment and investigate how these are affected by different percentage of end-users. The results show a better performance for Virtual Box than VMware and the other way around for I/O response. Nevertheless, the experiments shows that VBox have more robustness than VMware.

Cluster Computing, 2012

Abstract Energy efficiency and high computing power are basic design considerations across modern... more Abstract Energy efficiency and high computing power are basic design considerations across modern-day computing solutions due to different concerns such as system performance, operational cost, and environmental issues. Desktop Grid and Volunteer ...

The Journal of Supercomputing, 2013

Lecture Notes in Computer Science, 2013

ABSTRACT Platform as a Service providers deliver development and run-time environments for applic... more ABSTRACT Platform as a Service providers deliver development and run-time environments for applications that are hosted on the Cloud. In this paper, we present a Platform as a Service model constructed over a desktop-based Cloud infrastructure for developing high performance computing applications taking advantage of unused resources opportunis-tically. We highlight the key concepts and features of the platform, as well as its innovation on an opportunistic computing and we present the results of several tests showing the performance of the proposed model.

La investigación científica y tecnológica se apoya cada vez más en sistemas de cómputo de alto de... more La investigación científica y tecnológica se apoya cada vez más en sistemas de cómputo de alto desempeño para incrementar su calidad y alcances. Para lograr sistemas de este tipo en el contexto colombiano, se requiere lograr la integración los recursos limitados existentes en un grid o una grilla de alcance nacional conectada a través de la red RENATA. Con el propósito de aunar los esfuerzos de las universidades colombianas que trabajan en computación de alto desempeño ha surgido la iniciativa nacional Grid Colombia. Este artículo presenta la justificación de las necesidades de adelantar una iniciativa de este estilo y el trabajo adelantado con el objetivo de establecer una iniciativa nacional de computación en malla que sirva para potencia la capacidad investigativa de las instituciones colombianas.

This poster shows the performance evaluation of UnaCloud Opportunistic Computing IaaS. We analyze... more This poster shows the performance evaluation of UnaCloud Opportunistic Computing IaaS. We analyze from an HPC perspective, two virtualization frameworks Virtual Box and VMware ESXi and compare them over this particular opportunistic cloud environment. The benchmarks consist of two set of tests, High Performance Linpack and IOzone, that examine the performance and the Input/Output response. The purpose of the experiments is to evaluate the behavior of the different virtual environments over an opportunistic cloud environment and investigate how these are affected by different percentage of end-users. The results show a better performance for Virtual Box than VMware and the other way around for I/O response. Nevertheless, the experiments shows that VBox have more robustness than VMware.

Este artículo se enfoca en el análisis experimental de estrategias de implementación, incluyendo ... more Este artículo se enfoca en el análisis experimental de estrategias de implementación, incluyendo tecnologías clusters, para una infraestructura Grid, en un campus universitario. El mejor aprovechamiento en una institución educativa, debido a su estructura, es la utilización de tecnologías clúster, por el uso de salas homogéneas y, posteriormente, la unión de estos clusters mediante un middleware de Grilla. Se realizaron pruebas de desempeño con combinaciones de Beowulf [1] y Rocks [2] tanto en maquinas dedicadas como en maquinas virtuales, para clúster, y con Globus [3] [4] para grilla.

En el último año nuestro país a entrado a formar parte de los pocos países con iniciativa de Grid... more En el último año nuestro país a entrado a formar parte de los pocos países con iniciativa de Grid nacional, aunque esta tarea no ha sido fácil, se han adelantado esfuerzos en conjunto entre varias universidades de Colombia y entidades gubernamentales para cumplir los aspectos iniciales de esta propuesta. Este documento agrupa los planes generados de cada uno de los frentes formados en el primer evento que se realizó en Colombia el 9 de noviembre del año 2006 [1], muestra los proyectos que estamos realizando y los que van a contribuir a la formación tanto de la infraestructura como de la organización virtual Grid Colombia. Igualmente el articulo busca ser un documento inicial para el desarrollo del informe de avance del proyecto de formación del grid nacional. Por ultimo se muestra un estado actual enfocandose en la presentación de los proyectos que se realizaron en la pasada convocatoria de Colciencias y el MEN, adicionando las perspectivas futuras.

Este documento busca ser un primer articulo de socialización del proyecto, muestra como nacio la ... more Este documento busca ser un primer articulo de socialización del proyecto, muestra como nacio la idea de formar un Grid en Colombia, utilizando la red nacional académica de tecnologia avanzada RENATA, bajo que proyecto y el plan de trabajo que se realizo. También muestra los resumenes de los documentos realizados, paginas generadas con respecto a la iniciativa, adicionando los eventos que se realizaron con sus respectivas conclusiones de cada uno. Por ultimo se presenta el estado actual del proyecto, las perspectivas futuras, las universidades actualmente que forman el Grid y el plan de trabajo para el 2007.

PlatformasaServiceprovidersdeliverdevelopmentandrun- time environments for applications that are ... more PlatformasaServiceprovidersdeliverdevelopmentandrun- time environments for applications that are hosted on the Cloud. In this paper, we present a Platform as a Service model constructed over a desktop-based Cloud infrastructure for developing high performance computing applications taking advantage of unused resources opportunis- tically. We highlight the key concepts and features of the platform, as well as its innovation on an opportunistic computing and we present the results of several tests showing the performance of the proposed model.

UnaCloud is an opportunistic based cloud infras- tructure (IaaS) that allows to access on-demand ... more UnaCloud is an opportunistic based cloud infras- tructure (IaaS) that allows to access on-demand computing capabilities using commodity desktops. Although UnaCloud maximizes the use of idle resources to deploy virtual machines, it does not use energy-efficient resource allocation algorithms. In this paper, we design and develop different energy-aware algorithms to operate in an energy-efficient way and at the same time to guarantee the performance of the UnaCloud users. Performance tests with different algorithms and scenarios using real trace workloads from UnaCloud, show how different policies can change the energy consumption patterns and reduce the energy consumption in the opportunistic cloud infrastructure. The results show that some algorithms can reduce the energy-consumption power up to 30% over the percentage earned by the opportunistic environment.

ThepaperinvestigatestheinfluenceofDynamicVoltageFre- quency Scaling for bi-objective (makespan an... more ThepaperinvestigatestheinfluenceofDynamicVoltageFre- quency Scaling for bi-objective (makespan and energy consumption) Di- rected Acyclic task Graph scheduling on heterogeneous multi-processor platform. The proposed resolution method of solving conflicting crite- ria relies on Multi-Objective Evolutionary Algorithms. Two voltage fre- quency approaches are compared: one using only 2 levels (minimal and maximal) and the other one using a larger number. The approaches are benchmarked on applications with Laplace transformation and Gaussian elimination structures using the NSGAII algorithm. The results show that while the Two-level approach generates more discriminated solu- tions on the Pareto front, the solutions are of a lower quality than in the Multi-level approach.

The scalability of a computing system can be identified by at least three components: (a) size, (... more The scalability of a computing system can be identified by at least three components: (a) size, (b) geograph- ical distribution, and (c) administrative constraints. Newer paradigms, such as clouds, grids, and clusters bring in more parameters to the aforementioned list, namely heterogeneity, energy consumption, and transparency. To optimize the per- formance of a computing system, it is manner that exploits heterogeneity and is scalable. Moreover, newer systems also demand energy efficiency as an integral part of schedulers. In this paper, we evaluate the behavior of low complexity energy- efficient algorithms for scheduling. The set of experimental results showed that the evaluated heuristics perform as effi- ciently as related approaches; demonstrating their applicability and scalability for the considered problem.

Energy efficiency and High computing power are basic design considerations across modern-day comp... more Energy efficiency and High computing power are basic design considerations across modern-day computing solutions due to different concerns such as system performance, operational cost, and environmental issues. Opportunistic grid infrastructures offer computational power at low cost focused on harvesting idle computing cycles of existing commodity computing resources. Other than allowing to customize the end user offer, virtualization is considered as one key tech- niques to reduce energy consumption in large-scale systems and contributes to the scalability of the system. This paper presents an energy efficient approach for opportunistic grids based on virtualization. The experimental results show that virtualization significantly improves the energy efficiency of opportunistic grids compared with dedicated computing sys- tems without disturbing the end-user.